llama-3.1-70b by deepinfra Benchmarks

Stale Data

This model has not returned successful benchmark results recently. The data shown may be outdated.

Last benchmark: May 20, 2026

Benchmark Overview

Avg Tokens / Second

21.60

Avg Time to First Token (ms)

590.00

Runs Analysed

201

Last Updated

May 20, 2026, 06:37 AM

llama-3.1-70b streams at 21.60 tokens/second on average across the last 201 benchmark runs.
Performance fluctuated by 34.10 tokens/second (157.9% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 590.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 20, 2026, 06:37 AM based on 201 total samples.

Distribution of throughput measurements showing performance consistency across benchmark runs.

Historical performance trends showing how throughput has changed over the benchmarking period.

Provider	Model	Avg Toks/Sec	Min	Max	Avg TTF (ms)
deepinfra	llama-3.1-70b	21.60	5.30	39.40	590.00

The latest rolling average throughput is 21.60 tokens per second with an average time to first token of 590.00 ms across 201 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 20, 2026, 06:37 AM.